Automated Assessment of Neurodevelopment in Infants at Risk for Motor Disability

自动评估有运动障碍风险的婴儿的神经发育

• 批准号: 9765496
• 负责人: MICHELLE J. JOHNSON
• 金额: $ 71.11万
• 依托单位: UNIVERSITY OF PENNSYLVANIA
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-08-07 至 2024-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9765496
• 关键词: Age-Months; Algorithms; Asphyxia; Back; Behavior; Birth History; Brain Injuries; Calibration; Child; Childhood; Clinical; Collaborations; Complex; Computer Vision Systems; Consumption; Cross-Sectional Studies; Data; Data Analyses; Data Set; Development; Developmental Delay Disorders; Diagnosis; Diagnostic; Early Diagnosis; Early identification; Early treatment; Educational Status; Effectiveness; Foundations; Future; Generations; Goals; Gold; Hand Strength; Health; Hydrocephalus; Impairment; Infant; Infant Development; Infant Health; Infection; Intervention; Intuition; Knowledge; Lead; Life; Limb structure; Longitudinal Studies; Machine Learning; Measures; Medical; Monitor; Motor; Movement; Neurodevelopmental Disability; Neurologic; Neuronal Plasticity; Outcome; Pediatrics; Performance; Physically Handicapped; Pilot Projects; Play; Population; Posture; Predictive Value; Premature Birth; Risk; School-Age Population; Seizures; Supination; Survival Rate; System; Techniques; Testing; Time; Toy; Training; Translating; United States National Institutes of Health; Video Recording; Work; base; critical period; design; disability; drug abuse in pregnancy; early screening; functional disability; functional outcomes; health assessment; improved; infant monitoring; instrument; kinematics; machine learning algorithm; motor control; motor impairment; multimodality; neonatal stroke; neurodevelopment; novel strategies; pressure; prognostic tool; recruit; screening; sensor; sensor technology; skeletal; tool; vector

PROJECT SUMMARY/ABSTRACT The overall goal of this R01 project is to develop an automated assessment system that can capitalize on state of the art sensing technologies and machine learning algorithms to enable accurate and early detection of infants at risk for neurodevelopmental disabilities. In the USA, 1 in 10 infants are born at risk for these disabilities. For children with neurodevelopmental disabilities, early treatment in the first year of life improves long-term outcomes. However, we are currently held back by inadequacies of available clinical tests to measure and predict impairment. Existing tests are hard to administer, require specialized training, and have limited long- term predictive value. There is a critical need to develop an objective, accurate, easy-to-use tool for the early prediction of long-term physical disability. The field of pediatrics and infant development would greatly benefit from a quantitative score that would correlate with existing clinical measures used today to detect movement impairments in very young infants. To realize a new generation of tests that will be easy to administer, we will obtain large datasets of infants playing in an instrumented gym or simply being recorded while moving in a supine posture. Video and sensor data analyses will convert movement into feature vectors based on our knowledge of the problem domain. Our approach will use machine learning to relate these feature vectors to currently recommended clinical tests or other ground truth information. The power of this design is that algorithms can utilize many aspects of movement to produce the relevant scores. Our preliminary data allows us to lay the following aims: 1)Aim 1: To assess concurrent validity of a multimodal instrumented gym with existing clinical tools. Here, using 150 infants (75 with early brain injury and 75 controls), we will focus on converting data from an instrumented gym into estimates of the standard clinical tests; 2)Aim 2: To develop a computer vision-based algorithm to quantify infant motor performance from single camera video. Here using video data from 1200 infants (400 with early brain injury, 400 preterm without early brain injury, 400 controls), plus those gathered from Aim 1 and Aim 3, we will extract pose data from single-camera video recordings and convert these into kinematic features and relevant scores needed to classify infant movement; 3)Aim3: To discover the features related to long-term motor development. Here we will convert data collected longitudinally from 50 infants (25 with early brain injury and 25 controls) using both instrumented gym and video recordings into estimates standard clinical tests change over time and track features over developmental timescales. These three aims spearhead the use of real world behavior for movement scoring. Our aims will bring us closer to a universal non-invasive test for early detection of neurodevelopmental disabilities and lay the groundwork for long-term prediction of disability. But above all, it promises to scale to infants worldwide, producing an affordable tool to aid in infant health assessment.

项目概要/摘要 该 R01 项目的总体目标是开发一个自动化评估系统，该系统可以利用状态 艺术传感技术和机器学习算法可实现婴儿的准确和早期检测 有神经发育障碍的风险。在美国，十分之一的婴儿出生时就有患这些残疾的风险。 对于患有神经发育障碍的儿童，在生命的第一年进行早期治疗可以改善长期症状 结果。然而，我们目前因可用的临床测试不足以测量和评估而受到阻碍。 预测损伤。现有的测试难以管理，需要专门培训，并且长期效果有限。 期限预测值。迫切需要开发一种客观、准确、易于使用的工具来进行早期诊断。 预测长期身体残疾。儿科和婴儿发育领域将大大受益 来自与当今用于检测运动的现有临床测量相关的定量评分 非常年幼的婴儿的损伤。为了实现易于管理的新一代测试，我们将 获取婴儿在仪器仪表健身房玩耍或只是在婴儿室内移动时被记录的大量数据集 仰卧姿势。视频和传感器数据分析将基于我们的运动将运动转换为特征向量 问题领域的知识。我们的方法将使用机器学习将这些特征向量与 目前推荐的临床测试或其他真实信息。这个设计的力量在于 算法可以利用运动的许多方面来产生相关分数。我们的初步数据允许 我们设定以下目标： 1）目标 1：评估多式联运工具的并发有效性 拥有现有临床工具的健身房。在这里，我们使用 150 名婴儿（其中 75 名患有早期脑损伤，75 名对照）进行了研究 将专注于将来自仪器仪表健身房的数据转换为标准临床测试的估计值； 2）目标2： 开发一种基于计算机视觉的算法来量化婴儿的运动表现 单机视频。这里使用 1200 名婴儿的视频数据（400 名患有早期脑损伤，400 名早产儿） 没有早期脑损伤，400 个对照），加上从目标 1 和目标 3 收集的数据，我们将提取姿势数据 从单摄像头视频记录中提取数据并将其转换为运动学特征和所需的相关分数 对婴儿运动进行分类； 3）目标3：发现与长期运动发展相关的特征。 在这里，我们将对 50 名婴儿（25 名患有早期脑损伤和 25 名对照）纵向收集的数据进行转换 使用仪器化健身房和视频记录来估计标准临床测试随时间的变化 跟踪发育时间范围内的特征。这三个目标引领了现实世界行为的使用 运动得分。我们的目标将使我们更接近一种用于早期检测的通用非侵入性测试 神经发育障碍，并为残疾的长期预测奠定基础。但最重要的是，它 承诺扩展到全球婴儿，生产一种负担得起的工具来帮助婴儿健康评估。